Closes https://github.com/zed-industries/zed/issues/38690Closes#37353
### Background
On Windows, paths are normally separated by `\`, unlike mac and linux
where they are separated by `/`. When editing code in a project that
uses a different path style than your local system (e.g. remoting from
Windows to Linux, using WSL, and collaboration between windows and unix
users), the correct separator for a path may differ from the "native"
separator.
Previously, to work around this, Zed converted paths' separators in
numerous places. This was applied to both absolute and relative paths,
leading to incorrect conversions in some cases.
### Solution
Many code paths in Zed use paths that are *relative* to either a
worktree root or a git repository. This PR introduces a dedicated type
for these paths called `RelPath`, which stores the path in the same way
regardless of host platform, and offers `Path`-like manipulation APIs.
RelPath supports *displaying* the path using either separator, so that
we can display paths in a style that is determined at runtime based on
the current project.
The representation of absolute paths is left untouched, for now.
Absolute paths are different from relative paths because (except in
contexts where we know that the path refers to the local filesystem)
they should generally be treated as opaque strings. Currently we use a
mix of types for these paths (std::path::Path, String, SanitizedPath).
Release Notes:
- N/A
---------
Co-authored-by: Cole Miller <cole@zed.dev>
Co-authored-by: Piotr Osiewicz <24362066+osiewicz@users.noreply.github.com>
Co-authored-by: Peter Tripp <petertripp@gmail.com>
Co-authored-by: Smit Barmase <heysmitbarmase@gmail.com>
Co-authored-by: Lukas Wirth <me@lukaswirth.dev>
Closes https://github.com/zed-industries/zed/issues/37882
Previously, every piece of text in the agent panel was controlled by
`agent_font_size`. Although it is nice to only have one setting to tweak
that, it could be a bit misleading particularly because we use
monospaced and sans-serif fonts for different elements in the panel. Any
editor/textarea in the panel, whehter it is the main message editor or
the previous message editor, uses the buffer font. Therefore, I think it
is reasonable to expect that tweaking `buffer_font_size` would also
change the agent panel's usage of buffer fonts.
With this change, regular buffers and the agent panel's message editor
will always have the same size.
Release Notes:
- agent: Made the agent panel's textarea font size follow the font size
of regular buffers. They're now both controlled by the
`buffer_font_size` setting.
Nowadays, people don't expect @-mentioning a directory to include the
contents of all files within it. Doing so makes it very likely to
consume an undesirable amount of tokens.
By default, we'll now only include the path of the directory and let the
model decide how much to read via tools. We'll still include the
contents if no tools are available (e.g. "Minimal" profile is selected).
Release Notes:
- Agent Panel: Do not include the content of @-mentioned directories
when tools are available
<img width="598" height="311" alt="Screenshot 2025-09-11 at 9 39 12 PM"
src="https://github.com/user-attachments/assets/b526e648-37cf-4412-83a0-42037b9fc94d"
/>
This is for both ACP and the regular agent. Previously we would always
include the whole file, which can easily blow the context window on huge
files.
Release Notes:
- When `@mention`ing large files, the Agent Panel now send an outline of
the file instead of the whole thing.
This PR adds support for using external agents in SSH projects via ACP,
including automatic installation of Gemini CLI and Claude Code,
authentication with API keys (for Gemini) and CLI login, and custom
agents from user configuration.
Co-authored-by: maan2003 <manmeetmann2003@gmail.com>
Release Notes:
- agent: Gemini CLI, Claude Code, and custom external agents can now be
used in SSH projects.
---------
Co-authored-by: maan2003 <manmeetmann2003@gmail.com>
If we get back slash-commands that aren't supported, tell the user that
this is the problem.
Release Notes:
- Improve error messages for unsupported ACP slash-commands
---------
Co-authored-by: Conrad Irwin <conrad.irwin@gmail.com>
Closes: https://github.com/zed-industries/zed/issues/37089
Instead of looking for the gemini command on `$PATH`, by default we'll
install our own copy on demand under our data dir, as we already do for
language servers and debug adapters. This also means we can handle
keeping the binary up to date instead of prompting the user to upgrade.
Notes:
- The download is only triggered if you open a new Gemini thread
- Custom commands from `agent_servers.gemini` in settings are respected
as before
- A new `agent_servers.gemini.ignore_system_version` setting is added,
similar to the existing settings for language servers. It's `true` by
default, and setting it to `false` disables the automatic download and
makes Zed search `$PATH` as before.
- If `agent_servers.gemini.ignore_system_version` is `false` and no
binary is found on `$PATH`, we'll fall back to automatic installation.
If it's `false` and a binary is found, but the version is older than
v0.2.1, we'll show an error.
Release Notes:
- acp: By default, Zed will now download and use a private copy of the
Gemini CLI binary, instead of searching your `$PATH`. To make Zed search
your `$PATH` for Gemini CLI before attempting to download it, use the
following setting:
```
{
"agent_servers": {
"gemini": {
"ignore_system_version": false
}
}
}
```
Adds support for per-session prompt capabilities and capability changes
on the Zed side (ACP itself still only has per-connection static
capabilities for now), and uses it to reflect image support accurately
in 1PA threads based on the currently-selected model.
Release Notes:
- N/A
- Add pulsating animation for context creases while they're loading
- Add spinner in message editors (replacing send button) during the
window where sending has been requested, but we haven't finished loading
the message contents to send to the model
- During the same window, ignore further send requests, so we don't end
up sending the same message twice if you mash enter while loading is in
progress
- Wait for context to load before rewinding the thread when sending an
edited past message, avoiding an empty-looking state during the same
window
Release Notes:
- N/A
This PR makes it so that all kinds of @-mentions start loading their
context as soon as they are confirmed. Previously, we were waiting to
load the context for file, symbol, selection, and rule mentions until
the user's message was sent. By kicking off loading immediately for
these kinds of context, we can support adding selections from unsaved
buffers, and we make the semantics of @-mentions more consistent.
Loading all kinds of context eagerly also makes it possible to simplify
the structure of the MentionSet and the code around it. Now MentionSet
is just a single hash map, all the management of creases happens in a
uniform way in `MessageEditor::confirm_completion`, and the helper
methods for loading different kinds of context are much more focused and
orthogonal.
Release Notes:
- N/A
---------
Co-authored-by: Conrad <conrad@zed.dev>
The `PromptCapabilities` introduced in previous PRs were only getting
set on the main message editor and not for the editors in user messages.
This caused a bug where mentions would disappear after resending the
message, and for the completion provider to be limited to files.
Release Notes:
- N/A
The completion provider was already limiting the mention kinds according
to `acp::PromptCapabilities`. However, it was still using
`ContentBlock::EmbeddedResource` when
`acp::PromptCapabilities::embedded_context` was `false`. We will now use
`ResourceLink` in that case making it more complaint with the
specification.
Release Notes:
- N/A
Instead of holding a connection for potentially long LSP queries (e.g.
rust-analyzer might take minutes to look up a definition), disconnect
right after sending the initial request and handle the follow-up
responses later.
As a bonus, this allows to cancel previously sent request on the local
Collab clients' side due to this, as instead of holding and serving the
old connection, local clients now can stop previous requests, if needed.
Current PR does not convert all LSP requests to the new paradigm, but
the problematic ones, deprecating `MultiLspQuery` and moving all its
requests to the new paradigm.
Release Notes:
- Improved resource usage when querying LSP over Collab
---------
Co-authored-by: David Kleingeld <git@davidsk.dev>
Co-authored-by: Mikayla Maki <mikayla@zed.dev>
Co-authored-by: David Kleingeld <davidsk@zed.dev>
This removes around 900 unnecessary clones, ranging from cloning a few
ints all the way to large data structures and images.
A lot of these were fixed using `cargo clippy --fix --workspace
--all-targets`, however it often breaks other lints and needs to be run
again. This was then followed up with some manual fixing.
I understand this is a large diff, but all the changes are pretty
trivial. Rust is doing some heavy lifting here for us. Once I get it up
to speed with main, I'd appreciate this getting merged rather sooner
than later.
Release Notes:
- N/A
- Clean up failed load tasks for mentions that require async processing
- When dragging and dropping files, hold onto added worktrees until any
async processing has completed; this fixes a bug when dragging items
from outside the project
Release Notes:
- N/A
Highlight them as errors in the editor, and add a leading space when
sending them so users don't hit the odd behavior when sending these
commands to the SDK.
Release Notes:
- N/A
Note that (at least for now) this only works for creases in the "new
message" editor, not when editing past messages. That's because we don't
have the original image available when putting together the creases for
past messages, only the base64-encoded language model content.
Release Notes:
- N/A
- Support adding ImageContent to messages through copy/paste and through
path completions
- Ensure images are fully converted to LanguageModelImageContent before
sending them to the model
- Update ACP crate to v0.0.24 to enable passing image paths through the
protocol
Release Notes:
- N/A
---------
Co-authored-by: Conrad Irwin <conrad.irwin@gmail.com>